Generating transition states of chemical reactions via distance-geometry-based flow matching
This work addresses the challenge of exploring reaction mechanisms for chemists by providing a computational method to accelerate TS discovery, though it is incremental as it builds on existing flow matching and distance geometry concepts.
The paper tackles the problem of predicting transition states (TSs) for chemical reactions by proposing TS-DFM, a flow matching framework that operates in molecular distance geometry space, resulting in a 30% improvement in structural accuracy over the previous state-of-the-art method on the Transition1X dataset.
Transition states (TSs) are crucial for understanding reaction mechanisms, yet their exploration is limited by the complexity of experimental and computational approaches. Here we propose TS-DFM, a flow matching framework that predicts TSs from reactants and products. By operating in molecular distance geometry space, TS-DFM explicitly captures the dynamic changes of interatomic distances in chemical reactions. A network structure named TSDVNet is designed to learn the velocity field for generating TS geometries accurately. On the benchmark dataset Transition1X, TS-DFM outperforms the previous state-of-the-art method React-OT by 30\% in structural accuracy. These predicted TSs provide high-quality initial structures, accelerating the convergence of CI-NEB optimization. Additionally, TS-DFM can identify alternative reaction paths. In our experiments, even a more favorable TS with lower energy barrier is discovered. Further tests on RGD1 dataset confirm its strong generalization ability on unseen molecules and reaction types, highlighting its potential for facilitating reaction exploration.